merge

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 ckpt_00560000-kat-ema-pruned.ckpt filter=lfs diff=lfs merge=lfs -text
 ckpt_00840000-kat-ema-pruned.ckpt filter=lfs diff=lfs merge=lfs -text
+vae-ft-ema-560000-ema-pruned.ckpt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,4 +1,16 @@
+---
+license: mit
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+inference: false
+---
 # Improved Autoencoders
+
+## Utilizing
+These weights are intended to be used with the original [CompVis Stable Diffusion codebase](https://github.com/CompVis/stable-diffusion). If you are looking for the model to use with the D🧨iffusers library, [come here](https://huggingface.co/CompVis/stabilityai/sd-vae-ft-ema).
+
 ## Decoder Finetuning
 We publish two kl-f8 autoencoder versions, finetuned from the original [kl-f8 autoencoder](https://github.com/CompVis/latent-diffusion#pretrained-autoencoding-models).
 The first, _ft-EMA_, was resumed from the original checkpoint, trained for 313198 steps and uses EMA weights.
@@ -14,8 +26,8 @@ _Original kl-f8 VAE vs f8-ft-EMA vs f8-ft-MSE_
 |----------|---------|------|--------------|---------------|---------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
 |          |         |      |              |               |               |                                                                                   |                                                                                                 |
 | original | 246803        | 4.99 | 23.4 +/- 3.8 | 0.69 +/- 0.14 | 1.01 +/- 0.28 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip                            | as used in SD                                                                                   |
-| ft-EMA   | 560001        | 4.42 | 23.8 +/- 3.9 | 0.69 +/- 0.13 | 0.96 +/- 0.27 | https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/blob/main/ckpt_00560000-kat-ema-pruned.ckpt | slightly better overall, with EMA                                                               |
-| ft-MSE   | 840001        | 4.70 | 24.5 +/- 3.7 | 0.71 +/- 0.13 | 0.92 +/- 0.27 | https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/blob/main/ckpt_00840000-kat-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
+| ft-EMA   | 560001        | 4.42 | 23.8 +/- 3.9 | 0.69 +/- 0.13 | 0.96 +/- 0.27 | https://huggingface.co/stabilityai/sd-vae-ft-ema-original/resolve/main/vae-ft-ema-560000-ema-pruned.ckpt | slightly better overall, with EMA                                                               |
+| ft-MSE   | 840001        | 4.70 | 24.5 +/- 3.7 | 0.71 +/- 0.13 | 0.92 +/- 0.27 | https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
 
 
 ### LAION-Aesthetics 5+ (256x256, subset, 10000 images)
@@ -23,8 +35,8 @@ _Original kl-f8 VAE vs f8-ft-EMA vs f8-ft-MSE_
 |----------|-----------|------|--------------|---------------|---------------|-----------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
 |          |           |      |              |               |               |                                                                                   |                                                                                                 |
 | original | 246803         | 2.61 | 26.0 +/- 4.4 | 0.81 +/- 0.12 | 0.75 +/- 0.36 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip                            | as used in SD                                                                                   |
-| ft-EMA   | 560001          | 1.77 | 26.7 +/- 4.8 | 0.82 +/- 0.12 | 0.67 +/- 0.34 | https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/blob/main/ckpt_00560000-kat-ema-pruned.ckpt | slightly better overall, with EMA                                                               |
-| ft-MSE   | 840001          | 1.88 | 27.3 +/- 4.7 | 0.83 +/- 0.11 | 0.65 +/- 0.34 | https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/blob/main/ckpt_00840000-kat-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
+| ft-EMA   | 560001          | 1.77 | 26.7 +/- 4.8 | 0.82 +/- 0.12 | 0.67 +/- 0.34 | https://huggingface.co/stabilityai/sd-vae-ft-ema-original/resolve/main/vae-ft-ema-560000-ema-pruned.ckpt | slightly better overall, with EMA                                                               |
+| ft-MSE   | 840001          | 1.88 | 27.3 +/- 4.7 | 0.83 +/- 0.11 | 0.65 +/- 0.34 | https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
 
 
 ### Visual
@@ -37,25 +49,25 @@ _Visualization of reconstructions on  256x256 images from the COCO2017 validatio
 </p>
 
 <p align="center">
-<img src=eval/ae-decoder-tuning-reconstructions/merged/00025_merged.png />
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00025_merged.png />
 </p>
 
 <p align="center">
-<img src=eval/ae-decoder-tuning-reconstructions/merged/00011_merged.png />
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00011_merged.png />
 </p>
 
 <p align="center">
-<img src=eval/ae-decoder-tuning-reconstructions/merged/00037_merged.png />
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00037_merged.png />
 </p>
 
 <p align="center">
-<img src=eval/ae-decoder-tuning-reconstructions/merged/00043_merged.png />
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00043_merged.png />
 </p>
 
 <p align="center">
-<img src=eval/ae-decoder-tuning-reconstructions/merged/00053_merged.png />
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00053_merged.png />
 </p>
 
 <p align="center">
-<img src=eval/ae-decoder-tuning-reconstructions/merged/00029_merged.png />
+<img src=https://huggingface.co/stabilityai/stable-diffusion-decoder-finetune/resolve/main/eval/ae-decoder-tuning-reconstructions/merged/00029_merged.png />
 </p>

ckpt_00840000-kat-ema-pruned.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6a580b13a5bc05a5e16e4dbb80608ff2ec251a162311590c1f34c013d7f3dab
-size 334695179